Original article: PYBACT: AN ALGORITHM FOR BACTERIAL IDENTIFICATION

PyBact is a software written in Python for bacterial identification. The code simulates the predefined behavior of bacterial species by generating a simulated data set based on the frequency table of biochemical tests from diagnostic microbiology textbook. The generated data was used for predictive model construction by machine learning approaches and results indicated that the classifiers could accurately predict its respective bacterial class with accuracy in excess of 99 %.

[1]  Chartchalerm Isarankura-Na-Ayudhya,et al.  Quantitative structure-imprinting factor relationship of molecularly imprinted polymers. , 2007, Biosensors & bioelectronics.

[2]  Apilak Worachartcheewan,et al.  Identification of metabolic syndrome using decision tree analysis. , 2010, Diabetes research and clinical practice.

[3]  Chartchalerm Isarankura-Na-Ayudhya,et al.  Prediction of GFP spectral properties using artificial neural network , 2007, J. Comput. Chem..

[4]  Apilak Worachartcheewan,et al.  Modeling the activity of furin inhibitors using artificial neural network. , 2009, European journal of medicinal chemistry.

[5]  Ellen Jo Baron,et al.  Manual of clinical microbiology , 1975 .

[6]  S. Bascomb,et al.  Identification of bacteria by computer: theory and programming. , 1973, Journal of general microbiology.

[7]  C. Nantasenamat,et al.  Prediction of bond dissociation enthalpy of antioxidant phenols by support vector machine. , 2008, Journal of molecular graphics & modelling.

[8]  Chartchalerm Isarankura-Na-Ayudhya,et al.  A practical overview of quantitative structure-activity relationship , 2009 .

[9]  S. Bascomb,et al.  Identification of bacteria by computer: general aspects and perspectives. , 1973, Journal of general microbiology.

[10]  Apilak Worachartcheewan,et al.  Lower BMI cutoff for assessing the prevalence of metabolic syndrome in Thai population , 2010, Acta Diabetologica.

[11]  Apilak Worachartcheewan,et al.  Predicting the free radical scavenging activity of curcumin derivatives , 2011 .

[12]  Chartchalerm Isarankura-Na-Ayudhya,et al.  Advances in computational methods to predict the biological activity of compounds , 2010, Expert opinion on drug discovery.

[13]  Chartchalerm Isarankura-Na-Ayudhya,et al.  Modeling the LPS Neutralization Activity of Anti-Endotoxins , 2009, Molecules.

[14]  Sebastian Bassi,et al.  A Primer on Python for Life Science Researchers , 2007, PLoS Comput. Biol..

[15]  W Frederiksen,et al.  Possible misidentification of Haemophilus aphrophilus as Pasteurella gallinarum. , 2001, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[16]  Chartchalerm Isarankura-Na-Ayudhya,et al.  QSAR model of the quorum-quenching N-acyl-homoserine lactone lactonase activity , 2008 .

[17]  S. Lapage,et al.  A review of numerical methods in bacterial identification , 2004, Antonie van Leeuwenhoek.

[18]  Virapong Prachayasittikul,et al.  Quantitative prediction of imprinting factor of molecularly imprinted polymers by artificial neural network , 2005, J. Comput. Aided Mol. Des..

[19]  P H SNEATH,et al.  NEW APPROACHES TO BACTERIAL TAXONOMY: USE OF COMPUTERS. , 1964, Annual review of microbiology.

[20]  M Giacomini,et al.  Artificial neural network based identification of environmental bacteria by gas-chromatographic and electrophoretic data. , 2000, Journal of microbiological methods.

[21]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[22]  S. Abbott,et al.  Bacterial Identification for Publication: When Is Enough Enough? , 2002, Journal of Clinical Microbiology.